Use web_fetch for API documentation

data/prompts/agent-coding.md

@@ -80,7 +80,7 @@ Do not guess at API behavior. Do not rely on pattern matching from similar-looki
 
 **Procedure:**
 1. Identify the specific API/framework/library in use (Qt, React, Go stdlib, etc.)
-2. If uncertain about any method, property, or behavior, fetch the official docs via `curl` or `shell`
+2. If uncertain about any method, property, or behavior, fetch the official docs via the `web_fetch` tool
 3. Read the relevant sections before implementing
 4. Cite what you learned when explaining your implementation
 
@@ -92,15 +92,15 @@ Do not guess at API behavior. Do not rely on pattern matching from similar-looki
 - Working with positioning, layout, or scrolling APIs (these are notoriously tricky)
 
 **How to fetch docs:**
-```bash
+```text
 # Qt documentation
-curl -s "https://doc.qt.io/qt-6/qml-qtquick-listview.html" | grep -A10 "methodName"
+web_fetch(url="https://doc.qt.io/qt-6/qml-qtquick-listview.html")
 
 # Go stdlib
-go doc package.Function
+web_fetch(url="https://pkg.go.dev/std")
 
 # MDN for web APIs
-curl -s "https://developer.mozilla.org/en-US/docs/Web/API/..."
+web_fetch(url="https://developer.mozilla.org/en-US/docs/Web/API/")
 ```
 
 This is not optional. Guessing at APIs wastes time, breaks code, and frustrates users.

doc/prompt-audit.md

@@ -32,7 +32,7 @@ The embedded `system_prompt.md` is identical for every agent profile. It contain
 - ~100 lines of **9P namespace reference** (session management, ctl commands, examples)
 - Large **tool-first table** mapping tasks→tools (lsp_*, gui_*, memory_*)
 - **Sandbox & Bypass** section
-- **API documentation fetching** section (curl examples)
+- **API documentation fetching** section (`web_fetch` examples)
 
 Agents that can't run `ollie-9p` (copilot, librarian, explorer) pay the token cost for all of it. The model sees instructions about tools it doesn't have.